© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 5503
    Prev
    Next
    INDEX
    Explanations

    funds raised or paid

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    人æķ°
    -0.09
    é¢Ŀ
    -0.09
    thon
    -0.09
    è´«è¡Ģ
    -0.09
    AIN
    -0.09
    é«ĺé¢Ŀ
    -0.09
    chor
    -0.08
    åĨĽè®Ń
    -0.08
    åĩ¡äºĭ
    -0.08
    æĮģç»Ńæİ¨è¿Ľ
    -0.08
    POSITIVE LOGITS
    ics
    0.09
    主è¦ģçĶ¨äºİ
    0.09
    æīĭ段
    0.09
     rom
    0.09
    æĪĸèĢħåħ¶ä»ĸ
    0.08
    åĪ°ä½į
    0.08
    vak
    0.08
    çĩĥ
    0.08
    èĭ±çī¹
    0.08
    bx
    0.08
    Activations Density 0.015%

    No Known Activations